Re: [PATCH 9/9] perf kvm stat report: Add option to analyze specific VM
On 8/5/13 2:57 AM, Xiao Guangrong wrote: On 08/03/2013 04:05 AM, David Ahern wrote: Add an option to analyze a specific VM within a data file. This allows the collection of kvm events for all VMs and then analyze data for each VM (or set of VMs) individually. Interesting. But how can we know which pid is the guest's pid after collecting the info. Even if the .data file is moved to another box to do off-analyze? Up to the user to be able to leverage the option by collecting what ever information is needed to correlate a qemu pid with a guest VM. I have 2 use cases. In one I have a set of shell scripts for managing VMs: Id ProfilePID IP AddressDescription -- - --- 01 ubuntu10 - 172.16.128.51 Ubuntu 10.04 LTS 02 f12-x86_64 8841172.16.128.52 Fedora 12, x86_64 05 f10-i386 - 172.16.128.55 Fedora 10, i386 07 f16-i386 - 172.16.128.57 08 f16-x86_64 - 172.16.128.58 09 rhel5.5-i386 14716 172.16.128.59 RHEL 5.5, i386 10 f10-x86_64 - 172.16.128.60 12 rhel47-vm1 - 172.16.128.62 rhel4.7 - 32-bit 13 f17- 172.16.128.63 Fedora 17, x86_64 15 f14- 172.16.128.65 Fedora 14 - x86_64 16 f10-ppc- 172.16.128.66 17 f12-ppc- 172.16.128.67 19 f16-ppc- 172.16.128.69 20 f16-i386-2 - 172.16.128.70 clone of f16-i386 21 f18-controller 29590 172.16.128.71 cloud controller 22 f1829541 172.16.128.72 Fedora 18 - x86_64 Collecting that information allows me to correlate kvm data to a VM pid. I can collect the events for the system and then analyze for a specific VM. In the second use case (product based) there are 2 VMs and a different qemu binary name (along with command line arguments) for telling them apart. David -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 9/9] perf kvm stat report: Add option to analyze specific VM
On 08/03/2013 04:05 AM, David Ahern wrote: > Add an option to analyze a specific VM within a data file. This > allows the collection of kvm events for all VMs and then analyze > data for each VM (or set of VMs) individually. Interesting. But how can we know which pid is the guest's pid after collecting the info. Even if the .data file is moved to another box to do off-analyze? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 9/9] perf kvm stat report: Add option to analyze specific VM
On 08/03/2013 04:05 AM, David Ahern wrote: Add an option to analyze a specific VM within a data file. This allows the collection of kvm events for all VMs and then analyze data for each VM (or set of VMs) individually. Interesting. But how can we know which pid is the guest's pid after collecting the info. Even if the .data file is moved to another box to do off-analyze? -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 9/9] perf kvm stat report: Add option to analyze specific VM
On 8/5/13 2:57 AM, Xiao Guangrong wrote: On 08/03/2013 04:05 AM, David Ahern wrote: Add an option to analyze a specific VM within a data file. This allows the collection of kvm events for all VMs and then analyze data for each VM (or set of VMs) individually. Interesting. But how can we know which pid is the guest's pid after collecting the info. Even if the .data file is moved to another box to do off-analyze? Up to the user to be able to leverage the option by collecting what ever information is needed to correlate a qemu pid with a guest VM. I have 2 use cases. In one I have a set of shell scripts for managing VMs: Id ProfilePID IP AddressDescription -- - --- 01 ubuntu10 - 172.16.128.51 Ubuntu 10.04 LTS 02 f12-x86_64 8841172.16.128.52 Fedora 12, x86_64 05 f10-i386 - 172.16.128.55 Fedora 10, i386 07 f16-i386 - 172.16.128.57 08 f16-x86_64 - 172.16.128.58 09 rhel5.5-i386 14716 172.16.128.59 RHEL 5.5, i386 10 f10-x86_64 - 172.16.128.60 12 rhel47-vm1 - 172.16.128.62 rhel4.7 - 32-bit 13 f17- 172.16.128.63 Fedora 17, x86_64 15 f14- 172.16.128.65 Fedora 14 - x86_64 16 f10-ppc- 172.16.128.66 17 f12-ppc- 172.16.128.67 19 f16-ppc- 172.16.128.69 20 f16-i386-2 - 172.16.128.70 clone of f16-i386 21 f18-controller 29590 172.16.128.71 cloud controller 22 f1829541 172.16.128.72 Fedora 18 - x86_64 Collecting that information allows me to correlate kvm data to a VM pid. I can collect the events for the system and then analyze for a specific VM. In the second use case (product based) there are 2 VMs and a different qemu binary name (along with command line arguments) for telling them apart. David -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/